Publication

Abstract : Massive Open Online Courses (MOOCs) is an emerging model in the field of education, which has data about learners from various industries and universities to enhance learning. However, these courses are facing tremendous dropout with the expansion in the figures of the enrolled learners at various stages. In this paper, we are proposing a three-dimensional model: learner categorization, course categorization and learner background categorization, to acquire a deeper insight of the issue. This analysis model analyses the individual need of each learner along the three dimensions to diminish the dropout rate. In this model, each dimension is examined using various data mining techniques to understand the behavioral patterns of learners. Furthermore, this analysis also explores the interdependencies among the three dimensions to understand course participation and knowledge dissemination among the learners, employing the association rules. We have also examined some of the factors leading to dropout in MOOC courses. The results from the study suggest certain remedial measures to transform failures to success, thereby, enhancing learner engagement and course completion rate.